Title :
Complexity-regularized multiresolution density estimation
Author :
Willett, Rebecca M. ; Nowak, Robert D.
Author_Institution :
Rice Univ., Houston, TX
Abstract :
The density estimation method proposed in this paper employs piecewise polynomial fits on adaptive dyadic partitions. The proposed estimator enjoys the minimax adaptivity associated with wavelet-based density estimators as well as the following additional advantages: estimates are guaranteed to be nonnegative, theoretical bounds provide an indication of performance even for small sample sizes, and the method can be extended to free-degree piecewise polynomial estimation, which allows the data to adaptively determine the smoothness of the underlying basis functions
Keywords :
encoding; estimation theory; piecewise polynomial techniques; adaptive dyadic partition; density estimation method; free-degree piecewise polynomial estimation; piecewise polynomial fit; wavelet-based density estimator; Codes; Estimation error; Heart; Maximum likelihood estimation; Minimax techniques; Polynomials; Q measurement; Smoothing methods; Spatial resolution; Upper bound;
Conference_Titel :
Information Theory, 2004. ISIT 2004. Proceedings. International Symposium on
Conference_Location :
Chicago, IL
Print_ISBN :
0-7803-8280-3
DOI :
10.1109/ISIT.2004.1365342